linux-kernel - Re: [PATCH v3 2/2] irqchip/gic-v3-its: Balance initial LPI affinity across CPUs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <d3a6435b-bc1f-e518-6461-2ebff72bbc59@huawei.com>
Date:   Wed, 18 Mar 2020 12:22:09 +0000
From:   John Garry <john.garry@...wei.com>
To:     Marc Zyngier <maz@...nel.org>, <linux-kernel@...r.kernel.org>,
        <linux-arm-kernel@...ts.infradead.org>
CC:     chenxiang <chenxiang66@...ilicon.com>,
        Zhou Wang <wangzhou1@...ilicon.com>,
        Ming Lei <ming.lei@...hat.com>,
        Jason Cooper <jason@...edaemon.net>,
        Thomas Gleixner <tglx@...utronix.de>,
        "luojiaxing@...wei.com" <luojiaxing@...wei.com>
Subject: Re: [PATCH v3 2/2] irqchip/gic-v3-its: Balance initial LPI affinity
 across CPUs

I may have an idea about this:
irq 196, cpu list 0-31, effective list 82

Just going back to comment on the code:

> +/*
> + * As suggested by Thomas Gleixner in:
> + * https://lore.kernel.org/r/87h80q2aoc.fsf@nanos.tec.linutronix.de
> + */
> +static int its_select_cpu(struct irq_data *d,
> +			  const struct cpumask *aff_mask)
> +{
> +	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
> +	cpumask_var_t tmpmask;
> +	int cpu, node;
> +
> +	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
> +		return -ENOMEM;
> +
> +	node = its_dev->its->numa_node;
> +
> +	if (!irqd_affinity_is_managed(d)) {
> +		/* First try the NUMA node */
> +		if (node != NUMA_NO_NODE) {
> +			/*
> +			 * Try the intersection of the affinity mask and the
> +			 * node mask (and the online mask, just to be safe).
> +			 */
> +			cpumask_and(tmpmask, cpumask_of_node(node), aff_mask);
> +			cpumask_and(tmpmask, tmpmask, cpu_online_mask);
> +
> +			/* If that doesn't work, try the nodemask itself */

So if tmpmsk is empty...

> +			if (cpumask_empty(tmpmask))
> +				cpumask_and(tmpmask, cpumask_of_node(node), cpu_online_mask);

  now the tmpmask may have no intersection with the aff_mask...

> +
> +			cpu = cpumask_pick_least_loaded(d, tmpmask);
> +			if (cpu < nr_cpu_ids)
> +				goto out;
> +
> +			/* If we can't cross sockets, give up */
> +			if ((its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144))
> +				goto out;
> +
> +			/* If the above failed, expand the search */
> +		}

SNIP

> +out:
> +	free_cpumask_var(tmpmask);
> +
> +	pr_debug("IRQ%d -> %*pbl CPU%d\n", d->irq, cpumask_pr_args(aff_mask), cpu);
> +	return cpu;
> +}
> +
>   static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
>   			    bool force)
>   {
> -	unsigned int cpu;
> -	const struct cpumask *cpu_mask = cpu_online_mask;
>   	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
>   	struct its_collection *target_col;
>   	u32 id = its_get_event_id(d);
> +	int cpu;
>   
>   	/* A forwarded interrupt should use irq_set_vcpu_affinity */
>   	if (irqd_is_forwarded_to_vcpu(d))
>   		return -EINVAL;
>   
> -       /* lpi cannot be routed to a redistributor that is on a foreign node */
> -	if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
> -		if (its_dev->its->numa_node >= 0) {
> -			cpu_mask = cpumask_of_node(its_dev->its->numa_node);
> -			if (!cpumask_intersects(mask_val, cpu_mask))
> -				return -EINVAL;
> -		}
> -	}
> -
> -	cpu = cpumask_any_and(mask_val, cpu_mask);
> +	if (!force)
> +		cpu = its_select_cpu(d, mask_val);
> +	else
> +		cpu = cpumask_pick_least_loaded(d, mask_val);
>   
> -	if (cpu >= nr_cpu_ids)
> +	if (cpu < 0 || cpu >= nr_cpu_ids)
>   		return -EINVAL;

Annotate missing code:

	if (cpu < 0 || cpu >= nr_cpu_ids)
		return -EINVAL;

	if (cpu != its_dev->event_map.col_map[id]) {
		its_inc_lpi_count(d, cpu);
		its_dec_lpi_count(d, its_dev->event_map.col_map[id]);
		target_col = &its_dev->its->collections[cpu];
		its_send_movi(its_dev, target_col, id);
		its_dev->event_map.col_map[id] = cpu;
		irq_data_update_effective_affinity(d, cpumask_of(cpu));
	}

So cpu may not be a member of mask_val. Hence the inconsistency of the 
affinity list and effective affinity. We could just drop the AND of the 
ITS node mask in its_select_cpu().

Anyway, I don't think that this should stop us testing.

Cheers,
John